Exploring Role-Based Human-Centered AI Alerts with Novel Wearable Sensors and Multi-Sensory Cues
As vehicles transition between manual control and varying levels of automation in response to roadway, weather, traffic, and system conditions, drivers frequently lack a clear understanding of the vehicle's current capability boundaries, the actions expected of them, and the urgency of required responses. These gaps elevate risk during safety-critical control transitions. This project designs and empirically evaluates role-based, human-centered artificial intelligence (AI) safety alerts delivered through novel wearable sensors (a smart ring and a haptic glove) and in-cabin interfaces (seat vibration, windshield visuals, and odor cues where feasible) to improve alert meaning, driver comprehension, and driving performance. The research proceeds in two phases using a driving simulator with conditional automation. Phase I employs repeated-measures, counterbalanced design to compare smart ring, glove-based, and seat-vibration cues during standardized, time-limited takeover events, including periods of driver distraction, with urgency manipulated through available lead time. Dependent measures include takeover and response timing, minimum time-to-collision, lane-keeping and speed stability, braking and steering profiles, control smoothness, and subjective ratings of workload, trust, clarity, and comfort. Phase II examines how AI role communication, information framing and tone (neutral, supportive, stern) affect driver understanding, workload, and trust calibration when delivered through multi-sensory interfaces. Mixed-effects models will account for repeated events within drivers. The project will deliver implemented alert prototypes, empirical evidence on whether wearable sensors provide measurable safety benefits over traditional seat vibration, a validated approach for communicating AI support roles and tone, and design guidance for transparent, higher-meaning driver alerts. Results will support agencies, vehicle manufacturers, and suppliers in refining alert strategies that reduce confusion, improve response quality, and promote appropriate trust calibration during automated driving.
Language
- English
Project
- Status: Active
- Funding: $214,479.00
-
Contract Numbers:
69A3552348323
-
Sponsor Organizations:
Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590 -
Managing Organizations:
2400 6th Street, NW
Washington, DC United States 20059 -
Project Managers:
Bruner, Britain
-
Performing Organizations:
1 Washington Sq
San Jose, California United States 95192 -
Principal Investigators:
Huang, Gaojian
- Start Date: 20260803
- Expected Completion Date: 20270503
- Actual Completion Date: 0
- USDOT Program: University Transportation Centers
Subject/Index Terms
- TRT Terms: Artificial intelligence; Autonomous vehicle handover; Autonomous vehicles; Drivers; Driving simulators; Psychological trust; Sensors; Vibration; Warning systems
- Subject Areas: Data and Information Technology; Highways; Safety and Human Factors; Vehicles and Equipment;
Filing Info
- Accession Number: 01999720
- Record Type: Research project
- Source Agency: Research and Education for Promoting Safety (REPS) University Transportation Center
- Contract Numbers: 69A3552348323
- Files: UTC, RIP
- Created Date: Aug 19 2026 11:47AM